README.md

metadata

tags:
  - summarization
  - summary
  - booksum
  - long-document
  - long-form
license:
  - apache-2.0
  - bsd-3-clause
datasets:
  - kmfoda/booksum
metrics:
  - rouge
inference: false
model-index:
  - name: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP14
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 23.5177
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 4.668
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 16.6091
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 20.3174
            verified: true
          - name: loss
            type: loss
            value: 3.2174887657165527
            verified: true
          - name: gen_len
            type: gen_len
            value: 57.1966
            verified: true

long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP14

This model is a fine-tuned version of pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 on the kmfoda/booksum dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0006
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.02
• num_epochs: 2

Framework versions

• Transformers 4.22.0
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1